From 9ae409a05a0980ae70590303a83d983011831a80 Mon Sep 17 00:00:00 2001 From: Markus Heiser Date: Fri, 12 Aug 2022 17:46:20 +0200 Subject: [PATCH] [mod] add locale.get_engine_locale to get predictable results The match_language function sometimes returns incorrect results which is why a new function get_engine_locale is required. A bugfix of the match_language is not easily possible, because there is almost no documentation for it and already the call parameters are undefined. E.g. the function processes values like the ones from yahoo:: "yahoo": [ "ar", ... "zh_chs", "zh_cht" ] The get_engine_locale has been documented in detail, there is a clear description of the assumptions as well as the requirements and approximation rules (read doc-string for more details):: Argument ``engine_locales`` is a python dict that maps *SearXNG locales* to corresponding *engine locales*: : { # SearXNG string : engine-string 'ca-ES' : 'ca_ES', 'fr-BE' : 'fr_BE', 'fr-CA' : 'fr_CA', 'fr-CH' : 'fr_CH', 'fr' : 'fr_FR', ... 'pl-PL' : 'pl_PL', 'pt-PT' : 'pt_PT' } .. hint:: The *SearXNG locale* string has to be known by babel! In the following you will find a comparison: >>> import babel.languages >>> from searx.utils import match_language >>> from searx.locales import get_engine_locale Assume we have an engine that supports the follwoing locales: >>> lang_list = { ... "zh-CN": "zh_CN", ... "zh-HK": "zh_HK", ... "nl-BE": "nl_BE", ... "fr-CA": "fr_CA", ... } Assumption: A. When a user selects a language the results should be optimized according to the selected language. B. When user selects a language and a territory the results should be optimized with first priority on territory and second on language. ---- Example: (Assumption A.) A user selects region 'zh-TW' which should end in zh_HK hint: CN is 'Hans' and HK ('Hant') fits better to TW ('Hant') >>> get_engine_locale('zh-TW', lang_list) 'zh_HK' >>> lang_list[match_language('zh-TW', lang_list)] 'zh_CN' ---- Example: (Assumption A.) A user selects only the language 'zh' which should end in CN >>> get_engine_locale('zh', lang_list) 'zh_CN' >>> lang_list[match_language('zh', lang_list)] 'zh_CN' ---- Example: (Assumption B.) A user selects region 'fr-BE' which should end in nl-BE hint: priority should be on the territory the user selected. If the user prefers 'fr' he will select 'fr' without a region tag. >>> get_engine_locale('fr-BE', lang_list, default='unknown') 'nl_BE' >>> match_language('fr-BE', lang_list, fallback='unknown') 'fr-CA' ---- Example: (Assumption A.) A user selects only the language 'fr' which should end in fr_CA >>> get_engine_locale('fr', lang_list) 'fr_CA' >>> lang_list[match_language('fr', lang_list)] 'fr_CA' ---- The difference in priority on the territory is best shown with a engine that supports the following locales: >>> lang_list = { ... "fr-FR": "fr_FR", ... "fr-CA": "fr_CA", ... "en-GB": "en_GB", ... "nl-BE": "nl_BE", ... } ---- Example: (Assumption A.) A user selects only a language >>> get_engine_locale('en', lang_list) 'en_GB' >>> match_language('en', lang_list) 'en-GB' hint: the engine supports fr_FR and fr_CA since no territory is given, fr_FR takes priority .. >>> get_engine_locale('fr', lang_list) 'fr_FR' >>> lang_list[match_language('fr', lang_list)] 'fr_FR' ---- Example: (Assumption B.) A user selects region 'fr-BE' which should end in nl-BE >>> get_engine_locale('fr-BE', lang_list) 'nl_BE' >>> lang_list[match_language('fr-BE', lang_list)] 'fr_FR' ---- If the user selects a language and there are two locales like the following: >>> lang_list = { ... "fr-BE": "fr_BE", ... "fr-CH": "fr_CH", ... } >>> >>> get_engine_locale('fr', lang_list) 'fr_BE' >>> lang_list[match_language('fr', lang_list)] 'fr_BE' Looks like both functions return the same value, but match_language depends on the order of the dictionary (which is not predictable): >>> lang_list = { ... "fr-CH": "fr_CH", ... "fr-BE": "fr_BE", ... } >>> get_engine_locale('fr', lang_list) 'fr_BE' >>> lang_list[match_language('fr', lang_list)] 'fr_CH' >>> The get_engine_locale selects the locale by looking at the "population percent" and this percentage has an higher amount in BE (68.%) compared to CH (21%) Signed-off-by: Markus Heiser --- searx/locales.py | 137 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 137 insertions(+) diff --git a/searx/locales.py b/searx/locales.py index 3deff6863..227c95051 100644 --- a/searx/locales.py +++ b/searx/locales.py @@ -10,6 +10,8 @@ import pathlib from babel import Locale from babel.support import Translations +import babel.languages +import babel.core import flask_babel import flask from flask.ctx import has_request_context @@ -150,3 +152,138 @@ def locales_initialize(directory=None): LOCALE_NAMES[tag] = get_locale_descr(locale, dirname) if locale.text_direction == 'rtl': RTL_LOCALES.add(tag) + + +def get_engine_locale(searxng_locale, engine_locales, default=None): + """Return engine's language (aka locale) string that best fits to argument + ``searxng_locale``. + + Argument ``engine_locales`` is a python dict that maps *SearXNG locales* to + corresponding *engine locales*: + + : { + # SearXNG string : engine-string + 'ca-ES' : 'ca_ES', + 'fr-BE' : 'fr_BE', + 'fr-CA' : 'fr_CA', + 'fr-CH' : 'fr_CH', + 'fr' : 'fr_FR', + ... + 'pl-PL' : 'pl_PL', + 'pt-PT' : 'pt_PT' + } + + .. hint:: + + The *SearXNG locale* string has to be known by babel! + + If there is no direct 1:1 mapping, this functions tries to narrow down + engine's language (locale). If no value can be determined by these + approximation attempts the ``default`` value is returned. + + Assumptions: + + A. When user select a language the results should be optimized according to + the selected language. + + B. When user select a language and a territory the results should be + optimized with first priority on terrirtory and second on language. + + First approximation rule (*by territory*): + + When the user selects a locale with terrirtory (and a language), the + territory has priority over the language. If any of the offical languages + in the terrirtory is supported by the engine (``engine_locales``) it will + be used. + + Second approximation rule (*by language*): + + If "First approximation rule" brings no result or the user selects only a + language without a terrirtory. Check in which territories the language + has an offical status and if one of these territories is supported by the + engine. + + """ + # pylint: disable=too-many-branches + + engine_locale = engine_locales.get(searxng_locale) + + if engine_locale is not None: + # There was a 1:1 mapping (e.g. "fr-BE --> fr_BE" or "fr --> fr_FR"), no + # need to narrow language nor territory. + return engine_locale + + locale = babel.Locale.parse(searxng_locale, sep='-') + + # SearXNG's selected locale is not supported by the engine .. + + if locale.territory: + # Try to narrow by *offical* languages in the territory (??-XX). + + for official_language in babel.languages.get_official_languages(locale.territory, de_facto=True): + searxng_locale = official_language + '-' + locale.territory + engine_locale = engine_locales.get(searxng_locale) + if engine_locale is not None: + return engine_locale + + # Engine does not support one of the offical languages in the territory or + # there is only a language selected without a territory. + + # Now lets have a look if the searxng_lang (the language selected by the + # user) is a offical language in other territories. If so, check if + # engine does support the searxng_lang in this other territory. + + if locale.language: + + searxng_lang = locale.language + if locale.script: + searxng_lang += '_' + locale.script + + terr_lang_dict = {} + for territory, langs in babel.core.get_global("territory_languages").items(): + if not langs.get(searxng_lang, {}).get('official_status'): + continue + terr_lang_dict[territory] = langs.get(searxng_lang) + + # first: check fr-FR, de-DE .. is supported by the engine + + territory = locale.language.upper() + if terr_lang_dict.get(territory): + searxng_locale = locale.language + '-' + territory + engine_locale = engine_locales.get(searxng_locale) + if engine_locale is not None: + return engine_locale + + # second: sort by population_percent and take first match + + # drawback of "population percent": if there is a terrirtory with a + # small number of people (e.g 100) but the majority speaks the + # language, then the percentage migth be 100% (--> 100 people) but in + # a different terrirtory with more people (e.g. 10.000) where only 10% + # speak the language the total amount of speaker is higher (--> 200 + # people). + # + # By example: The population of Saint-Martin is 33.000, of which 100% + # speak French, but this is less than the 30% of the approximately 2.5 + # million Belgian citizens + # + # - 'fr-MF', 'population_percent': 100.0, 'official_status': 'official' + # - 'fr-BE', 'population_percent': 38.0, 'official_status': 'official' + + terr_lang_list = [] + for k, v in terr_lang_dict.items(): + terr_lang_list.append((k, v)) + + for territory, _lang in sorted(terr_lang_list, key=lambda item: item[1]['population_percent'], reverse=True): + searxng_locale = locale.language + '-' + territory + engine_locale = engine_locales.get(searxng_locale) + if engine_locale is not None: + return engine_locale + + # No luck: narrow by "language from territory" and "territory from language" + # does not fit to a locale supported by the engine. + + if engine_locale is None: + engine_locale = default + + return default